|
|
|
|
|
|
|
import onnxruntime as ort |
|
import numpy |
|
from PIL import Image |
|
|
|
ort_sess = ort.InferenceSession('model.onnx') |
|
classes = [ "train" , "seaplane" , "motorbus" , "airplane" , "stair" , "bicycle" , "bus" , "car" , "crosswalk" , "hydrant" , "motorcycle" , "mountain" , "stairs" , "tow truck" , "traffic light" , "traffic sign" , "truck" , ] |
|
|
|
img = Image.open("image.jpg").convert('RGB') |
|
img = img.resize((300, 300 * img.size[1] // img.size[0]), Image.ANTIALIAS) |
|
inp_numpy = numpy.array(img)[None].astype('float32') |
|
|
|
|
|
class_scores = ort_sess.run(None, {'input': inp_numpy})[0][0] |
|
|
|
|
|
|
|
print("") |
|
print("class_scores", class_scores) |
|
print("Class : ", classes[class_scores.argmax()]) |
